Papers › Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restoration

Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restoration

1 Oct 2024arXiv:2410.00418archive 2025-07-28

Guy Ohayon, Tomer Michaeli, Michael Elad

Photo-realistic image restoration algorithms are typically evaluated by distortion measures (e.g., PSNR, SSIM) and by perceptual quality measures (e.g., FID, NIQE), where the desire is to attain the lowest possible distortion without compromising on perceptual quality. To achieve this goal, current methods commonly attempt to sample from the posterior distribution, or to optimize a weighted sum of a distortion loss (e.g., MSE) and a perceptual quality loss (e.g., GAN). Unlike previous works, this paper is concerned specifically with the optimal estimator that minimizes the MSE under a constraint of perfect perceptual index, namely where the distribution of the reconstructed images is equal to that of the ground-truth ones. A recent theoretical result shows that such an estimator can be constructed by optimally transporting the posterior mean prediction (MMSE estimate) to the distribution of the ground-truth images. Inspired by this result, we introduce Posterior-Mean Rectified Flow (PMRF), a simple yet highly effective algorithm that approximates this optimal estimator. In particular, PMRF first predicts the posterior mean, and then transports the result to a high-quality image using a rectified flow model that approximates the desired optimal transport map. We investigate the theoretical utility of PMRF and demonstrate that it consistently outperforms previous methods on a variety of image restoration tasks.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2410.00418")

Code

Syntology Ran 4 of 10 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 3 ran with no contract checked.

By repository: official repository: 10 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ohayonguy/PMRF officialmentioned in papermentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

10 samples harvested; 4 ran; 0 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
3ran
6unverified

Licence: 0 of the 10 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from ohayonguy/PMRF. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

calculate_points ohayonguy/PMRF/evaluation/calculate_landmark_distance.py official repository ran MIT (permissive) · 236cf18a7e5a0db9 · report
conv3x3 ohayonguy/PMRF/evaluation/awing_arch.py official repository ran · our draft was wrong MIT (permissive) · cd28335574411d48 · report
img2tensor ohayonguy/PMRF/evaluation/calculate_cos_dist.py official repository ran MIT (permissive) · 8b5cf3d00508f17b · report
load_image_torch ohayonguy/PMRF/evaluation/calculate_cos_dist.py official repository ran MIT (permissive) · 6d7e52beb54f602e · report
calculate_points ohayonguy/PMRF/evaluation/awing_arch.py official repository unverified MIT (permissive) · 37e244c7bbaccec7 · report
init_alignment_model ohayonguy/PMRF/evaluation/calculate_landmark_distance.py official repository unverified MIT (permissive) · 60130eacf5484058 · report
load_image ohayonguy/PMRF/evaluation/calculate_cos_dist.py official repository unverified MIT (permissive) · d8d6d771a1dadff4 · report
mesh_grid ohayonguy/PMRF/utils/basicsr_custom.py official repository unverified MIT (permissive) · 794d4f7fc184e7e5 · report
pdf2 ohayonguy/PMRF/utils/basicsr_custom.py official repository unverified MIT (permissive) · 321b9c73d589eb9e · report
sigma_matrix2 ohayonguy/PMRF/utils/basicsr_custom.py official repository unverified MIT (permissive) · e3444ff2b9d24600 · report

Tasks

Blind Face RestorationImage ColorizationImage DenoisingImage InpaintingImage RestorationImage Super-ResolutionSSIM

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Blind Face Restoration CelebA-Test PMRF Deg. 30.67 #15 of 15 Archive leaderboard report
Blind Face Restoration CelebA-Test PMRF FID 37.46 #15 of 15 Archive leaderboard report
Blind Face Restoration CelebA-Test PMRF NIQE 4.118 #15 of 15 Archive leaderboard report
Blind Face Restoration CelebA-Test PMRF PSNR 26.37 #15 of 15 Archive leaderboard report
Blind Face Restoration CelebA-Test PMRF SSIM 0.7073 #15 of 15 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections